Lane line data detection method, device, equipment and medium

Abstract

The embodiment of the invention discloses a lane line data detection method and device, equipment and a medium. The method comprises the following steps: acquiring data of a current road section where an automatic driving vehicle is located and to-be-searched data; wherein the current road section data is obtained based on a high-precision map, and the to-be-searched data comprises a to-be-searched lane; determining a lane line set according to the current road section data and the to-be-searched data; wherein the lane line set comprises a plurality of lane line coordinate points; determining a projection coordinate point and a target coordinate point of the automatic driving vehicle on each lane line based on the coordinate points of the plurality of lane lines in the lane line set; and determining a lane line data list of the to-be-searched lane according to the projection coordinate point, the target coordinate point and the lane line set. According to the technical scheme, the lane line data detection accuracy and reliability of the automatic driving vehicle under complex traffic environment and severe weather conditions can be improved, and powerful support is provided for decision making, path planning and safe driving of the automatic driving vehicle.

Description

Technical Field

[0001] The present invention relates to the field of autonomous driving technology, and in particular to a lane line data detection method, device, equipment and medium. Background Art

[0002] With the development of autonomous driving technology, autonomous driving technology and advanced driving assistance systems are increasingly used in vehicle driving. In order to ensure that the vehicle's lane position is determined while driving, lane line recognition and prediction on the vehicle's driving path become particularly important.

[0003] Existing lane recognition technologies mostly rely on on-board sensors such as cameras and radars. These methods may have problems with inaccurate or delayed recognition in complex environments. For example, in bad weather conditions, the camera may not be able to clearly capture the lane lines; and at night or in low light conditions, the recognition of lane lines will also be affected. In addition, the recognition range of on-board sensors is limited, and it is difficult to predict the lane lines at a long distance in front of the vehicle, which limits the path planning ability of the autonomous driving system in complex traffic environments. Summary of the invention

[0004] The present invention provides a lane line data detection method, device, equipment and medium, which can improve the accuracy and reliability of lane line data detection of autonomous driving vehicles in complex traffic environments and severe weather conditions, and provide strong support for the decision-making, path planning and safe driving of autonomous driving vehicles.

[0005] According to one aspect of the present invention, a lane line data detection method is provided, comprising:

[0006] Acquire the current road section data and the data to be searched where the autonomous driving vehicle is located; wherein the current road section data is acquired based on a high-precision map, and the data to be searched includes lanes to be searched;

[0007] Determine a lane line set according to the current road section data and the data to be searched; wherein the lane line set includes a plurality of lane line coordinate points;

[0008] Determine a projection coordinate point and a target coordinate point of the autonomous driving vehicle on each lane line based on the coordinate points of the plurality of lane lines in the lane line set;

[0009] A lane line data list of a lane to be searched is determined according to the projection coordinate point, the target coordinate point and the lane line set.

[0010] Optionally, the data to be searched also includes a search distance and a search direction;

[0011] Determining a lane line set according to the current road section data and the data to be searched includes:

[0012] Starting from the current road section, traversing each road section and lane in the high-precision map based on the search distance to obtain a target path;

[0013] The coordinate points of each lane line on the high-precision map are determined according to the search direction and the target path, and the coordinate points of each lane line are used as a lane line set.

[0014] Optionally, determining a projection coordinate point and a target coordinate point of the autonomous driving vehicle on each lane line based on the coordinate points of the plurality of lane lines in the lane line set includes:

[0015] Get the coordinate points of the autonomous driving vehicle;

[0016] The lane line set is traversed, and the target coordinate point of the autonomous driving vehicle and the projection coordinate point on each lane line are determined based on each lane line coordinate point and the vehicle coordinate point.

[0017] Optionally, traversing the lane line set and determining the target coordinate point of the autonomous driving vehicle and the projection coordinate point on each lane line based on each lane line coordinate point and the vehicle coordinate point, comprises:

[0018] For each lane line coordinate point, obtain a first lane line coordinate point and a second lane line coordinate point; wherein the first lane line coordinate point is the currently traversed lane line coordinate point, and the second lane line coordinate point is the next coordinate point of the first lane line coordinate point;

[0019] Determine projection parameters according to the first lane line coordinate point, the second lane line coordinate point and the vehicle coordinate point;

[0020] Determine the target coordinate point according to the projection parameters and the set data range;

[0021] The projection coordinate point of the autonomous driving vehicle on each lane line is determined according to the projection parameters, the first lane line coordinate point and the vehicle coordinate point.

[0022] Optionally, determining projection parameters according to the first lane line coordinate point, the second lane line coordinate point and the vehicle coordinate point includes:

[0023] Determine first vector data according to the first lane line coordinate point and the vehicle coordinate point;

[0024] Determine second vector data according to the second lane line coordinate point and the vehicle coordinate point;

[0025] Projection parameters are determined based on the first vector data and the second vector data.

[0026] Optionally, the set data range includes a first set data range and a second set data range;

[0027] Determine the target coordinate point based on the projection parameters and set data range, including:

[0028] If the projection parameter is within the first setting range, taking the first lane line coordinate point as the target coordinate point;

[0029] If the projection parameter is within the second setting range, the third lane line coordinate point is used as the target coordinate point; wherein the third lane line coordinate point is the previous coordinate point of the first lane line coordinate point.

[0030] Optionally, the lane line data list includes lane line type, lane line length and lane line starting point distance data;

[0031] Determining a lane line data list of a lane to be searched according to the projection coordinate point, the target coordinate point and the lane line set includes:

[0032] Determine the initial current traversal distance, the initial lane line type and the initial lane line starting point distance based on the projection coordinate point and the target coordinate point;

[0033] Starting from the next lane line coordinate point of the target coordinate point, the traversal is performed, and updating the current traversal distance, lane line type and lane line starting point distance data based on the traversed lane line coordinate point;

[0034] Determine the length data of each lane line based on the current traversal distance;

[0035] The lane line type, lane line length data and lane line starting point distance data obtained in each traversal are recorded and formed into a lane line data list.

[0036] According to another aspect of the present invention, there is provided a lane line data detection device, comprising:

[0037] A data acquisition module, used to acquire the current road section data and the data to be searched where the autonomous driving vehicle is located; wherein the current road section data is acquired based on a high-precision map, and the data to be searched includes lanes to be searched;

[0038] A lane line set determination module, used to determine a lane line set according to the current road section data and the data to be searched; wherein the lane line set includes a plurality of lane line coordinate points;

[0039] A coordinate point determination module, used to determine a projection coordinate point and a target coordinate point of the autonomous driving vehicle on each lane line based on the coordinate points of a plurality of lane lines in the lane line set;

[0040] A lane line data list determination module is used to determine a lane line data list of a lane to be searched based on the projection coordinate point, the target coordinate point and the lane line set.

[0041] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0042] at least one processor; and

[0043] a memory communicatively connected to the at least one processor; wherein,

[0044] The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the lane line data detection method described in any embodiment of the present invention.

[0045] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the lane line data detection method described in any embodiment of the present invention when executed.

[0046] The technical solution of the embodiment of the present invention is to obtain the current road section data and the data to be searched where the autonomous driving vehicle is located; wherein the current road section data is obtained based on a high-precision map, and the data to be searched includes lanes to be searched; a lane line set is determined based on the current road section data and the data to be searched; wherein the lane line set includes multiple lane line coordinate points; based on the coordinate points of multiple lane lines in the lane line set, the projection coordinate points and target coordinate points of the autonomous driving vehicle on each lane line are determined; and a lane line data list of the lane to be searched is determined based on the projection coordinate points, the target coordinate points and the lane line set. This technical solution can improve the accuracy and reliability of lane line data detection of autonomous driving vehicles in complex traffic environments and severe weather conditions, and provide strong support for decision-making, path planning and safe driving of autonomous driving vehicles.

[0047] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0049] Figure 1 is a flow chart of a lane line data detection method provided according to Embodiment 1 of the present invention;

[0050] Figure 2 is a flow chart of a lane line data detection method provided according to Embodiment 2 of the present invention;

[0051] Figure 3 is a structural schematic diagram of a lane line data detection device provided according to Embodiment 3 of the present invention;

[0052] Figure 4 It is a structural schematic diagram of an electronic device provided according to Embodiment 4 of the present invention. DETAILED DESCRIPTION

[0053] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0054] It should be noted that the terms "first", "second" and "target" in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0055] Embodiment 1

[0056] Figure 1 This is a flow chart of a lane line data detection method provided according to the first embodiment of the present invention. This embodiment is applicable to the case where an autonomous driving vehicle detects lane line data of an invisible road section. The method can be executed by a lane line data detection device. The lane line data detection device can be implemented in the form of hardware and / or software. The lane line data detection device can be configured in an electronic device with data processing capabilities. Figure 1 As shown, the method includes:

[0057] The technical solution of this embodiment can be run on a domain controller (Advanced Driver Assistance System Domain Controller, ADAS). Based on the future lane line identification method of the ADAS domain controller and high-precision map, it can use the real-time positioning information of the vehicle and the high-precision map data to predict the type of lane line on the vehicle's future path, and output its distance, length, and whether it can be crossed, so as to provide decision support for the automatic driving system. Among them, the ADAS domain controller is the core component used to implement the advanced driver assistance system (ADAS) in the car. It is responsible for processing key tasks such as perception, decision-making, execution, safety and communication by integrating a variety of sensors, actuators and control algorithms. The future lane can be understood as the use of high-precision maps to predict the lane line data on the planned route outside the current vehicle's recognition range, and can also identify the lanes within one kilometer of the set navigation route in the future.

[0058] S110, obtaining the current road section data where the autonomous driving vehicle is located and the data to be searched.

[0059] Among them, the current road section data is obtained based on the high-precision map, and the data to be searched includes the lane to be searched. In this embodiment, the ADAS domain controller includes a high-precision map and a fusion positioning module that can output the current UTM coordinate information of the vehicle. The current road section data may include the high-precision map section identification where the current autonomous driving vehicle is located. The road section identification in this embodiment can be represented by a road section ID. A high-precision map (HD map) is a high-precision map for autonomous driving, which expresses map elements such as roads, lanes, roadside traffic signs and ground signs. The map accuracy can be at the centimeter level. The lane to be searched can be understood as the high-precision map lane identification that needs to be searched, and the lane identification in this embodiment can be represented by a lane ID. The lane to be searched in this embodiment can be a lane that cannot be recognized by the current camera of the current autonomous driving vehicle, or it can be a search lane in the future road section that will be passed in the navigation path. It can be understood that the high-precision map in this embodiment may include each road section ID, and each road section contains multiple lane IDs. The data to be searched may include the lane to be searched, and may also include data such as the search distance and the search direction.

[0060] In this embodiment, the precise map section ID and the lane ID to be searched where the autonomous driving vehicle is located can be obtained, and data such as the distance to be searched and the direction to be searched can also be included.

[0061] S120: Determine a lane line set according to the current road section data and the data to be searched.

[0062] The lane line set includes multiple lane line coordinate points. The multiple lane line coordinate points included in the lane line set can be the road section information given by the high-precision map, and the lane line coordinate point data determined based on the data to be searched. In this embodiment, starting from the current road section of the vehicle, according to the road section information given by the high-precision map, the lane line coordinate point data determined by the search direction in the lane to be searched within the distance to be searched can be obtained by traversing the data to be searched.

[0063] In this embodiment, optionally, the data to be searched also includes a search distance and a search direction; a lane line set is determined based on the current road section data and the data to be searched, including: starting from the current road section, traversing each road section and lane in the high-precision map based on the search distance to obtain a target path; determining each lane line coordinate point on the high-precision map based on the search direction and the target path, and taking each lane line coordinate point as a lane line set.

[0064] Among them, the search distance can be a pre-set distance range based on the current autonomous driving vehicle to start the search. The search distance in this embodiment can be a search distance range of no more than two kilometers starting from the current autonomous driving vehicle, or it can be a distance range that can be navigated by a high-precision map. It can be set according to actual needs, and this embodiment does not limit this. The search direction can be understood as the direction to the left and right of the current autonomous driving vehicle. The target path can be a complete path obtained by splicing the lanes obtained by establishing each road section and lane in the high-precision map according to the search distance.

[0065] Specifically, in this embodiment, starting from the current section, the sections and lanes in the high-precision map are traversed based on the search distance, and the specific method for obtaining the target path can be starting from the section where the current vehicle is located, according to the connection relationship between the sections and lanes given by the high-precision map, traversing the subsequent sections and lanes until the traversal stop condition is met, and splicing the traversed lanes to obtain the target path. It can be understood that in this embodiment, each complete path in the high-precision map is divided into many sections; the lane IDs contained in each section are different, so if a continuous complete lane needs to be obtained, it is necessary to splice the lanes in the traversed section according to the connection relationship of the high-precision map to obtain the target path. Among them, the traversal stop condition may include reaching a specified search distance or encountering a section bifurcation. In this embodiment, the specific method for determining the coordinate points of each lane line on the high-precision map according to the search direction and the target path can be to select the lane line of the corresponding direction in the target path according to the search direction (the left or right side of the current autonomous driving vehicle) to obtain the coordinate points of each lane line in the target path, and use these lane line coordinate points as a lane line set. Furthermore, in this embodiment, the lane lines of the high-precision map are composed of coordinate points, so that a point sequence P composed of n coordinate points can be obtained = {p1, p2, ..., pn}, that is, the lane line set, where each point p i Contains (x i ,y i , t i ), x i For point p i The horizontal coordinate in the UTM coordinate system, y i For point p i The vertical coordinate in the UTM coordinate system, t i Point p i The lane line type may include the original lane line data provided by the high-precision map, and may include lane line type (dashed line, solid line, or fishbone line, etc.), triangle area and other data.

[0066] Through such a setting in this embodiment, it is possible to traverse the high-precision map sections and lanes, and determine the coordinate points of each lane line as a lane line set based on the data to be searched, so as to determine the data information of each lane line based on the lane line set.

[0067] S130. Determine the projection coordinate point and target coordinate point of the autonomous driving vehicle on each lane line based on the coordinate points of multiple lane lines in the lane line set.

[0068] Among them, the projection coordinate point can be understood as the projection coordinate point of the autonomous driving vehicle on the lane line. In this embodiment, the projection coordinate point of the autonomous driving vehicle on each lane line can be determined based on the coordinate points of each lane line in the lane line set and the coordinate point of the vehicle. Specifically, in this embodiment, starting from the first lane line coordinate point in the lane line set, vector calculation can be performed based on the first lane line coordinate point and the next adjacent lane line coordinate point and the coordinate point of the vehicle, so as to determine the projection coordinate point of the autonomous driving vehicle on each lane line using the data obtained by the vector calculation.

[0069] The target coordinate point can be understood as the lane line coordinate point behind the autonomous vehicle and closest to the autonomous vehicle. In this embodiment, starting from the first lane line coordinate point in the lane line set, vector calculation is performed based on the first lane line coordinate point and the next adjacent lane line coordinate point and the vehicle coordinate point, so as to determine the data range of the data obtained by the vector calculation to determine the target coordinate point of the autonomous vehicle.

[0070] S140. Determine a lane line data list of the lane to be searched according to the projection coordinate point, the target coordinate point and the lane line set.

[0071] The lane line data list may include a data list consisting of lane line types, distances from the starting point of the lane line to the vehicle, and lane line lengths of multiple lane line coordinate points. It can be understood that in this embodiment, each lane line coordinate point may correspond to a data information consisting of a lane line type, distances from the starting point of the lane line to the vehicle, and lane line length, and the data information consisting of multiple lane line types, distances from the starting point of the lane line to the vehicle, and lane line lengths corresponding to multiple lane line coordinate points respectively constitute the lane line data list.

[0072] In this embodiment, lane line data such as lane line type, distance between the lane line starting point and the vehicle, and lane line length can be determined based on the projection coordinate point and the target coordinate point, and then the lane line data is traversed and updated based on the lane line set to determine a list of lane line data in the lane to be searched.

[0073] The technical solution of the embodiment of the present invention is to obtain the current road section data and the data to be searched where the autonomous driving vehicle is located; wherein the current road section data is obtained based on a high-precision map, and the data to be searched includes lanes to be searched; a lane line set is determined based on the current road section data and the data to be searched; wherein the lane line set includes multiple lane line coordinate points; based on the coordinate points of multiple lane lines in the lane line set, the projection coordinate points and target coordinate points of the autonomous driving vehicle on each lane line are determined; and a lane line data list of the lane to be searched is determined based on the projection coordinate points, the target coordinate points and the lane line set. This technical solution can improve the accuracy and reliability of lane line data detection of autonomous driving vehicles in complex traffic environments and severe weather conditions, and provide strong support for decision-making, path planning and safe driving of autonomous driving vehicles.

[0074] Embodiment 2

[0075] Figure 2 This is a flow chart of a lane line data detection method provided according to the second embodiment of the present invention. This embodiment is optimized based on the above embodiment. The specific optimization is: based on the coordinate points of multiple lane lines in the lane line set, determine the projection coordinate points and target coordinate points of the autonomous driving vehicle on each lane line, including: obtaining the self-driving vehicle coordinate points; traversing the lane line set, and determining the target coordinate points of the autonomous driving vehicle and the projection coordinate points on each lane line based on each lane line coordinate point and the self-vehicle coordinate point. Figure 2 As shown, the method includes:

[0076] S210: Obtain the current road section data where the autonomous driving vehicle is located and the data to be searched.

[0077] Among them, the current road section data is obtained based on the high-precision map, and the data to be searched includes the lanes to be searched.

[0078] S220: Determine a lane line set according to the current road section data and the data to be searched.

[0079] The lane line set includes multiple lane line coordinate points.

[0080] S230: Obtain the vehicle coordinate point of the autonomous driving vehicle.

[0081] The ego vehicle coordinate point can be understood as the center point of the ego vehicle rear axle at the current location of the automatically accelerated vehicle. In this embodiment, the ego vehicle coordinate point of the autonomous driving vehicle can be directly obtained according to the fusion positioning in the ADAS domain controller.

[0082] S240, traverse the lane line set, and determine the target coordinate point of the autonomous driving vehicle and the projection coordinate point on each lane line based on each lane line coordinate point and the vehicle coordinate point.

[0083] In this embodiment, each lane line coordinate point in the lane line set can be traversed, and projection parameters can be determined based on the currently traversed lane line coordinate point and its next adjacent lane line coordinate point combined with the vehicle coordinate point. The coordinate point behind the vehicle and closest to the vehicle, i.e., the target coordinate point, can be determined based on the projection parameters and the currently traversed lane line coordinate point. Alternatively, the projection coordinate point can be determined based on the projection parameters and the next lane line coordinate point adjacent to the currently traversed lane line coordinate point.

[0084] In this embodiment, optionally, the lane line set is traversed, and the target coordinate point of the autonomous driving vehicle and the projection coordinate point on each lane line are determined based on each lane line coordinate point and the own vehicle coordinate point, including: for each lane line coordinate point, obtaining the first lane line coordinate point and the second lane line coordinate point; determining the projection parameters according to the first lane line coordinate point, the second lane line coordinate point and the own vehicle coordinate point; determining the target coordinate point according to the projection parameters and the set data range; determining the projection coordinate point of the autonomous driving vehicle on each lane line according to the projection parameters, the first lane line coordinate point and the own vehicle coordinate point.

[0085] Among them, the first lane line coordinate point is the lane line coordinate point currently traversed, and the second lane line coordinate point is the next coordinate point after the first lane line coordinate point. It can be understood that in this embodiment, for each lane line coordinate point, the lane line coordinate point currently being traversed can be obtained as the first lane line coordinate point, and the next lane line coordinate point after the lane line coordinate point currently being traversed can be taken as the second lane line coordinate point, and so on, the first lane line coordinate point and the second lane line coordinate point are determined in the same way for each lane line coordinate point. The projection parameter can be understood as the projection value obtained by performing calculation operations based on the first lane line coordinate point, the second lane line coordinate point and the vehicle coordinate point.

[0086] In this embodiment, the specific method of determining the projection parameters according to the first lane line coordinate point, the second lane line coordinate point and the vehicle coordinate point can be to obtain two vector data by vector calculation according to the first lane line coordinate point and the second lane line coordinate point and the vehicle coordinate point, and to obtain the projection parameters by formula calculation according to the two vector data. In this embodiment, the specific method of determining the target coordinate point according to the projection parameter and the set data range can be to determine different target coordinate points respectively according to whether the projection parameter is within the set data range.

[0087] In this embodiment, the projection coordinate point corresponding to the first lane coordinate point currently traversed by the vehicle can be set as p proj (x proj ,y proj ), the first lane line coordinate point can be p i (x i ,y i , t i ), the vehicle coordinates are (x veh ,y veh ), τ is the projection parameter, then in this embodiment, the projection coordinate point p of the autonomous driving vehicle on each lane line is determined according to the projection parameter, the first lane line coordinate point and the vehicle coordinate point proj (x proj ,y proj ) can be:

[0088] x proj =x i +τ*(x veh -x i );

[0089] y proj =y i +τ*(y veh -y i );

[0090] Furthermore, in this embodiment, the projection parameters and the coordinate point p of the second lane line can be used to calculate the lane line coordinates. i+1 (x i+1 ,y i+1 , t i+1 ) and the vehicle coordinate point to determine the projection coordinate point p of the autonomous driving vehicle on each lane line proj (x proj ,y proj ) can be:

[0091] x proj =x i+1 +(1-τ)*(x veh -x i+1 );

[0092] y proj =y i+1 +(1-τ)*(y veh -y i+1 );

[0093] It can be understood that in this embodiment, the target coordinate point p j It is the point behind the vehicle and closest to the vehicle. Projection coordinate point p proj (x proj ,y proj ) between point p j and p j+1 The coordinate points between .

[0094] Through such a setting in this embodiment, the projection point of the autonomous driving vehicle on each lane line can be calculated based on the coordinate points of each lane line in the traversed lane line set, so as to facilitate subsequent analysis and determine the data information of each lane line.

[0095] In this embodiment, optionally, projection parameters are determined based on the first lane line coordinate point, the second lane line coordinate point and the vehicle coordinate point, including: determining first vector data based on the first lane line coordinate point and the vehicle coordinate point; determining second vector data based on the second lane line coordinate point and the vehicle coordinate point; determining projection parameters based on the first vector data and the second vector data.

[0096] The first vector data may be data obtained by performing vector calculation on the coordinate point of the lane line currently traversed in the lane line set and the coordinate point of the vehicle. The second vector data may be data obtained by performing vector calculation on the coordinate point of the next lane line adjacent to the coordinate point of the lane line currently traversed in the lane line set and the coordinate point of the vehicle.

[0097] Specifically, in this embodiment, the vehicle coordinate point that can be output by fusion positioning is (x veh ,y veh ), which can be recorded as C, starting from the first lane line coordinate point p1 in the lane line set P, for each lane line coordinate point p i (i), which can be written as A is the coordinate point p of the lane line currently being traversed i (x i ,y i , t i ), i.e., the first lane line coordinate point; B can be the next point p adjacent to the lane line coordinate point currently being traversed. i+1 (x i+1 ,y i+1 , t i+1 ), i.e. the coordinate point of the second lane line;

[0098] In this embodiment, the first vector data AC calculated according to the first lane line coordinate point A and the vehicle coordinate point C can be (xveh -x i ,y veh -y i ); The second vector data BC calculated according to the second lane line coordinate point B and the vehicle coordinate point C can be (x veh -x i+1 ,y veh -y i+1 );

[0099] In this embodiment, the specific method of determining the projection parameter τ according to the first vector data AC and the second vector data BC may be:

[0100]

[0101] Through such a setting in this embodiment, projection parameters can be calculated based on the lane line coordinate points and the vehicle coordinate points in the lane line set, so as to determine the target coordinate points and the projection coordinate points based on the projection parameters, thereby improving data reliability.

[0102] In this embodiment, optionally, the set data range includes a first set data range and a second set data range; the target coordinate point is determined according to the projection parameters and the set data range, including: if the projection parameter is in the first set range, the first lane line coordinate point is used as the target coordinate point; if the projection parameter is in the second set range, the third lane line coordinate point is used as the target coordinate point.

[0103] The third lane line coordinate point is the previous coordinate point of the first lane line coordinate point. The first set data range may be a data range greater than or equal to 0 and less than or equal to 1; the second data range may be a data range greater than 1.

[0104] In this embodiment, the target coordinate point can be the lane line coordinate point where the traversal ends, and can be any lane line coordinate point in the lane line set. In this embodiment, the specific determination method of determining the target coordinate point based on the projection parameter and the set data range can be: if 0≤τ≤1, the first lane line coordinate point is used as the target coordinate point, that is, the index i is recorded as j, which means that the vehicle coordinate point C is between the first lane line coordinate point A and the second lane line coordinate point B; if τ>1, the previous coordinate point of the first lane line coordinate point is used as the target coordinate point, and the index i-1 is recorded as j, which means that the vehicle point C is after the first lane line coordinate point A and the second lane line coordinate point B. In this embodiment, the traversal can be stopped after the target coordinate point is determined, that is, the index j is determined. Furthermore, if the projection parameter τ<0, it is necessary to continue traversing the lane line set, which means that the vehicle coordinate point C is before the first lane line coordinate point A and the second lane line coordinate point B.

[0105] Through such a setting in this embodiment, different target coordinate points can be determined according to the data range of the projection parameter value, so that the coordinate point behind the vehicle and closest to the vehicle can be determined, so as to determine the distance of each lane line and other data information based on the target coordinate point, thereby improving the accuracy of the data.

[0106] S250, determining a lane line data list of a lane to be searched according to the projection coordinate point, the target coordinate point and the lane line set.

[0107] In this embodiment, optionally, the lane line data list includes lane line type, lane line length and lane line starting point distance data; the lane line data list of the lane to be searched is determined according to the projection coordinate point, the target coordinate point and the lane line set, including: determining the initial current traversal distance, the initial lane line type and the initial lane line starting point distance based on the projection coordinate point and the target coordinate point; starting the traversal from the lane line coordinate point next to the target coordinate point, and updating the current traversal distance, lane line type and lane line starting point distance data based on the traversed lane line coordinate point; determining each lane line length data based on the current traversal distance; recording the lane line type, lane line length data and lane line starting point distance data obtained in each traversal and forming a lane line data list.

[0108] The lane line type may include lane line type (dotted line, solid line or fishbone line, etc.), triangle area and other data. The lane line length may be understood as the length data corresponding to each lane line. The lane line starting point distance data may be understood as the distance data from the lane line starting point to the vehicle.

[0109] In this embodiment, based on the projection coordinate point projection coordinate point p proj (x proj ,y proj ) and the target coordinate point p j (x j ,y j , t j ) Determine the initial current traversal distance d cur , initial lane line type t and initial lane line starting point distance d start The specific method can be to initialize the current traversal distance Initialize lane line type t=t j , initialize the starting distance d of the current lane line start = 0. It can be understood that the initialized lane line type is the lane line type corresponding to the current projection point, and then the initial current traversal distance d is determined according to the projection point coordinate point and the target coordinate point. cur And the distance d from the starting point of the initial lane line start .

[0110] In this embodiment, the traversal may start from the next lane line coordinate point of the target coordinate point, and update the current traversal distance, lane line type and lane line starting point distance data based on the traversed lane line coordinate points. Specifically, the traversal distance may be updated from the index p j+1 Start traversing the point sequence P. Each time you traverse, you will update the current traversal distance. In this embodiment, when the lane line type changes and is different from the initial lane line type or the last recorded lane line type, the lane line data will be recorded once. That is, if the current traversal point p i t i ≠t, then the lane type t, the distance d from the lane start point to the vehicle can be start , lane length d cur Record the following information into the lane line data list. It should be noted that the current traversal distance data in this embodiment is a cumulative value, and each update will accumulate the last recorded traversal distance. Therefore, the current traversal data is data that is constantly increasing, and the distance from the lane line starting point to the vehicle is real-time data that is recorded once in real time every time the lane line type changes.

[0111] In this embodiment, the specific method for determining the length data of each lane line according to the current traversal distance is to subtract the distance of the last traversal from the current traversal distance to obtain the length data of the current lane line.

[0112] In this embodiment, each time the lane line changes, the lane line type, lane line length data and lane line starting point distance data obtained in each traversal will be recorded. After recording, the lane line type t=t i , update the starting distance d of the current lane line start =d cur (This can be understood as an assignment operation), continue the next traversal until all lane line coordinate points in the point column P of the lane line set are traversed, then a list containing the future lane line type, distance, and length can be output, that is, a lane line data list is formed. In this embodiment, through such a setting, each lane line coordinate point contained in the lane line set is traversed according to the projection coordinate point and the target coordinate point, and then a lane line data list of unknown lanes can be obtained, and the list can be used as a reference for the autonomous driving decision module, which can improve the lane line type detection accuracy and reliability of autonomous driving vehicles in complex traffic environments and severe weather conditions, provide strong support for vehicle decision-making, path planning and safe driving, and improve the safety and reliability of autonomous driving vehicles.

[0113] The technical solution of the embodiment of the present invention is to obtain the current road section data and the data to be searched where the autonomous driving vehicle is located; wherein the current road section data is obtained based on a high-precision map, and the data to be searched includes lanes to be searched; determine a lane line set according to the current road section data and the data to be searched; wherein the lane line set includes multiple lane line coordinate points; obtain the self-driving vehicle's own vehicle coordinate point; traverse the lane line set, and determine the target coordinate point of the autonomous driving vehicle and the projection coordinate point on each lane line based on each lane line coordinate point and the self-vehicle coordinate point; determine the lane line data list of the lane to be searched according to the projection coordinate point, the target coordinate point and the lane line set. This technical solution can improve the accuracy and reliability of lane line data detection of autonomous driving vehicles in complex traffic environments and severe weather conditions, and provide strong support for decision-making, path planning and safe driving of autonomous driving vehicles.

[0114] Embodiment 3

[0115] Figure 3 Schematic diagram of the structure of a lane line data detection device provided according to the third embodiment of the present invention. Figure 3 As shown, the device comprises:

[0116] The data acquisition module 310 is used to acquire the current road section data and the data to be searched where the autonomous driving vehicle is located; wherein the current road section data is acquired based on the high-precision map, and the data to be searched includes the lanes to be searched;

[0117] A lane line set determination module 320 is used to determine a lane line set according to the current road section data and the data to be searched; wherein the lane line set includes a plurality of lane line coordinate points;

[0118] A coordinate point determination module 330, for determining a projection coordinate point and a target coordinate point of the autonomous driving vehicle on each lane line based on the coordinate points of multiple lane lines in the lane line set;

[0119] The lane line data list determination module 340 is used to determine the lane line data list of the lane to be searched according to the projection coordinate point, the target coordinate point and the lane line set.

[0120] Optionally, the data to be searched also includes a search distance and a search direction;

[0121] The lane line set determination module 320 is specifically used to traverse each road section and lane in the high-precision map based on the search distance starting from the current road section to obtain the target path; determine the coordinate points of each lane line on the high-precision map according to the search direction and the target path, and use each lane line coordinate point as a lane line set.

[0122] Optionally, the coordinate point determination module 330 includes:

[0123] A self-vehicle coordinate point acquisition unit, used to acquire the self-vehicle coordinate point of the autonomous driving vehicle;

[0124] The traversal unit is used to traverse the lane line set and determine the target coordinate point of the autonomous driving vehicle and the projection coordinate point on each lane line based on each lane line coordinate point and the vehicle coordinate point.

[0125] Optionally, traverse the unit, including:

[0126] The lane line coordinate point acquisition subunit is used to acquire a first lane line coordinate point and a second lane line coordinate point for each lane line coordinate point; wherein the first lane line coordinate point is a currently traversed lane line coordinate point, and the second lane line coordinate point is a coordinate point after the first lane line coordinate point;

[0127] A projection parameter determination subunit, used to determine the projection parameters according to the first lane line coordinate point, the second lane line coordinate point and the vehicle coordinate point;

[0128] A target coordinate point determination subunit is used to determine the target coordinate point according to the projection parameters and the set data range;

[0129] The projection coordinate point determination subunit is used to determine the projection coordinate point of the autonomous driving vehicle on each lane line based on the projection parameters, the first lane line coordinate point and the vehicle coordinate point.

[0130] Optionally, the projection parameter determination subunit is specifically used to determine the first vector data based on the first lane line coordinate point and the vehicle coordinate point; determine the second vector data based on the second lane line coordinate point and the vehicle coordinate point; and determine the projection parameters based on the first vector data and the second vector data.

[0131] Optionally, the set data range includes a first set data range and a second set data range;

[0132] The target coordinate point determination subunit is specifically used to use the first lane line coordinate point as the target coordinate point if the projection parameter is within the first setting range; and use the third lane line coordinate point as the target coordinate point if the projection parameter is within the second setting range; wherein the third lane line coordinate point is the previous coordinate point of the first lane line coordinate point.

[0133] Optionally, the lane line data list includes lane line type, lane line length and lane line starting point distance data;

[0134] The lane line data list determination module 340 is specifically used to determine the initial current traversal distance, the initial lane line type and the initial lane line starting point distance based on the projection coordinate point and the target coordinate point; start traversal from the next lane line coordinate point of the target coordinate point, and update the current traversal distance, lane line type and lane line starting point distance data based on the traversed lane line coordinate point; determine the length data of each lane line based on the current traversal distance; record the lane line type, lane line length data and lane line starting point distance data obtained in each traversal and form a lane line data list.

[0135] A lane line data detection device provided in an embodiment of the present invention can execute a lane line data detection method provided in any embodiment of the present invention, and has functional modules and beneficial effects corresponding to the execution method.

[0136] Embodiment 4

[0137] Figure 4 1 is a schematic diagram of the structure of an electronic device provided according to Embodiment 4 of the present invention. The electronic device 10 is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0138] like Figure 4 As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0139] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0140] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the lane line data detection method.

[0141] In some embodiments, the lane data detection method may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the lane data detection method described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to perform the lane data detection method in any other appropriate manner (e.g., by means of firmware).

[0142] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0143] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0144] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0145] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0146] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0147] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0148] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0149] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A lane line data detection method, characterized in that: include: Acquire the current road section data and the data to be searched where the autonomous driving vehicle is located; wherein the current road section data is acquired based on a high-precision map, and the data to be searched includes lanes to be searched; Determine a lane line set according to the current road section data and the data to be searched; wherein the lane line set includes a plurality of lane line coordinate points; Determine a projection coordinate point and a target coordinate point of the autonomous driving vehicle on each lane line based on the coordinate points of the plurality of lane lines in the lane line set; A lane line data list of a lane to be searched is determined according to the projection coordinate point, the target coordinate point and the lane line set.

2. The method according to claim 1, characterized in that The data to be searched also includes a search distance and a search direction; Determining a lane line set according to the current road section data and the data to be searched includes: Starting from the current road section, traversing each road section and lane in the high-precision map based on the search distance to obtain a target path; The coordinate points of each lane line on the high-precision map are determined according to the search direction and the target path, and the coordinate points of each lane line are used as a lane line set.

3. The method according to claim 1, characterized in that: Determining a projection coordinate point and a target coordinate point of the autonomous driving vehicle on each lane line based on the coordinate points of the plurality of lane lines in the lane line set includes: Get the coordinate points of the autonomous driving vehicle; The lane line set is traversed, and the target coordinate point of the autonomous driving vehicle and the projection coordinate point on each lane line are determined based on each lane line coordinate point and the vehicle coordinate point.

4. The method according to claim 3, characterized in that Traversing the lane line set, determining the target coordinate point of the autonomous driving vehicle and the projection coordinate point on each lane line based on each lane line coordinate point and the vehicle coordinate point, including: For each lane line coordinate point, obtain a first lane line coordinate point and a second lane line coordinate point; wherein the first lane line coordinate point is the currently traversed lane line coordinate point, and the second lane line coordinate point is the next coordinate point of the first lane line coordinate point; Determine projection parameters according to the first lane line coordinate point, the second lane line coordinate point and the vehicle coordinate point; Determine the target coordinate point according to the projection parameters and the set data range; The projection coordinate point of the autonomous driving vehicle on each lane line is determined according to the projection parameters, the first lane line coordinate point and the vehicle coordinate point.

5. The method according to claim 4, characterized in that Determining projection parameters according to the first lane line coordinate point, the second lane line coordinate point and the vehicle coordinate point includes: Determine first vector data according to the first lane line coordinate point and the vehicle coordinate point; Determine second vector data according to the second lane line coordinate point and the vehicle coordinate point; Projection parameters are determined based on the first vector data and the second vector data.

6. The method according to claim 4, characterized in that The set data range includes a first set data range and a second set data range; Determine the target coordinate point based on the projection parameters and set data range, including: If the projection parameter is within the first setting range, taking the first lane line coordinate point as the target coordinate point; If the projection parameter is within the second setting range, the third lane line coordinate point is used as the target coordinate point; wherein the third lane line coordinate point is the previous coordinate point of the first lane line coordinate point.

7. The method according to claim 1, characterized in that The lane line data list includes lane line type, lane line length and lane line starting point distance data; Determining a lane line data list of a lane to be searched according to the projection coordinate point, the target coordinate point and the lane line set includes: Determine the initial current traversal distance, the initial lane line type and the initial lane line starting point distance based on the projection coordinate point and the target coordinate point; Starting from the next lane line coordinate point of the target coordinate point, the traversal is performed, and updating the current traversal distance, lane line type and lane line starting point distance data based on the traversed lane line coordinate point; Determine the length data of each lane line based on the current traversal distance; The lane line type, lane line length data and lane line starting point distance data obtained in each traversal are recorded and formed into a lane line data list.

8. A lane line data detection device, characterized in that: include: A data acquisition module, used to acquire the current road section data and the data to be searched where the autonomous driving vehicle is located; wherein the current road section data is acquired based on a high-precision map, and the data to be searched includes lanes to be searched; A lane line set determination module, used to determine a lane line set according to the current road section data and the data to be searched; wherein the lane line set includes a plurality of lane line coordinate points; A coordinate point determination module, used to determine a projection coordinate point and a target coordinate point of the autonomous driving vehicle on each lane line based on the coordinate points of a plurality of lane lines in the lane line set; A lane line data list determination module is used to determine a lane line data list of a lane to be searched based on the projection coordinate point, the target coordinate point and the lane line set.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the lane line data detection method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the lane line data detection method according to any one of claims 1 to 7 when executed.

Images